International Business Machines Corporation

Nayeem Islam

Trent Ray Jaeger

Jochen Liedtke

Vsevolod V Panteleenko

Liana Liyow Fong

Mark Steven Squillante

Ajei Sarat Gopal

Andreas Leonidas Prodromidis

Rangachari Anand

Daniel Charles Sturman

Colin James Parris

Vineet Singh

Alain Franck Gefflaut

James Edward Beck

Frederique-Anne Giraud

A method, apparatus and computer product that enables one or more computing devices to discover and use services over a network, which may be ad-hoc when the computing device is mobile. Service discovery is based on periodic multicasting of exported service descriptions to nearby devices over the (ad-hoc) network. Middleware enables a device to discover, advertise and use services. This enables software clients on the same device to share a service implementation (in the case of a local service) or to share an implementation proxy (in the case of a remote service). Each device being aware of the services (and service locations) that are currently available generally reduces the response time associated with accessing available services. While service descriptors are multicast and discovered, the service software is only downloaded on the device when the service is used. This enables economical resource management that is particularly useful for mobile devices.

Service framework for computing devices

A server complex including at least one hit server with item cache, used to process read and write operations relating to cached items from clients, and at least one miss server, serving as a link to other servers (e.g., web servers, file system servers, and databases) for receiving requests relayed from the hit server(s) which relate to non-cached items and for responding to same. The hit server is a general-purpose, generic, component, which is independent of concrete applications and is basically responsible for the performance; while a miss server is a highly-customizable component, which is responsible for flexibility, and is application specific. The inventive architecture provides improved performance whereby a server complex achieves exceptionally high throughput rates for local services (i.e., services using items in the local item cache); flexibility, whereby a server complex can support the enforcement of a variety of application-specific policies for item management, authentication, and item consistency; security, whereby a server complex can enable the verification of the source, integrity, and freshness of communications over untrusted links; and, scalability, whereby a server complex is expandable by adding server components and implementing customized item consistency policies.

Powerful and flexible server architecture

The invention provides the mechanism, hereinafter referred to as Flexible Dynamic Partitioning (FDP), to allocate and reallocate resources among scheduling schemes of many types for multicomputing environments. Resources can include, but are not limited to, processors, disks and communications connections. Partitioning of resources can be initiated by both application and system triggers. Once dynamic partitioning is triggered, FDP allows a partition to invoke a set of resource allocation functions associated with its partition. The reallocation function performs a set of resource matchings and determine the necessary resource movement among partitions.

Flexible dynamic partitioning of resources in a cluster computing environment

A system and method whereby a gang scheduling entity assembles a schedule of application tasks to be run on a plurality of distributed parallel processors for pre-set time intervals. The scheduling information, including an ordered set of applications and the length of the time interval, are provided to each of the node level schedulers for the relevant processors, and the node level schedulers assure that the tasks of the applications are executed, with context switching between tasks being controlled at the node level. Tasks from multiple applications can be scheduled simultaneously, with time sharing and space sharing being utilized in the schedule. The inventive system is dynamically scalable, with the gang scheduling entity restructuring the matrix schedule should dynamic re-partitioning result in addition or deletion of processors.

Gang scheduling for resource allocation in a cluster computing environment

A cache system in accordance with the present invention consists of one or more cache components and a set of one or more consistency-replacement functions. A cache component caches one or more items in its one or more cache entries. Items that hit in the cache can result in corresponding cache entries being read or written. Any valid entry in a cache component includes status information reflecting whether the entry has been accessed and whether it has been modified, and is linked to a consistency-action matrix that, in correspondence with the entry's status information and access type (i.e. read or write), determines what consistency action has to be executed in conjunction with the current entry access. Consistency actions and the consistency-action matrix are the inventive mechanisms for implementing cache-coherency and cache-replacement policies. Any valid entry in a cache is linked to a consistency-replacement function that implements one or more consistency and/or replacement policies. Consistency-replacement functions are application-specific and are implemented by means of the consistency-action matrix.

Flexible cache-coherency mechanism

An open architecture for arbitrarily combining data analysis algorithms and databases on the Internet where the data analysis algorithm and database may be from different vendors or suppliers. At the request of a customer, the two are combined on the fly while maintaining proper security and while enforcing some agreed upon payment from the customer to both the algorithm and database suppliers. In one embodiment, a message including an identifier of a user selected independent content provider and an identifier of a particular service associated with a service provider is sent to the service provider on a communication network. The user selected independent content provider is separate from the service provider. In response to the message, a computer executable code, which when executed by the content provider will cause the particular service to be performed against content controlled by the content provider, is sent from the service provider to the content provider. The computer executable code is executed by the content provider and at least partial results of the executing is returned to the user by way of the communication network.

Mechanism for combining data analysis algorithms with databases on the

A dynamic derivation mechanism is defined which enables limited permissions to be dynamically and flexibly derived for executables based upon their authenticated description. The dynamic derivation mechanism uses the authenticated description to determine the maximal permissions that individual principals can delegate to the content. A principal's maximal permissions for content define a superset of the rights that that principal will actually delegate to that content. Although the maximal permissions are derived from predefined specifications, the specifications can be sensitive to runtime state on the downloader's system or previous delegations to enable the dynamic (i.e., runtime) derivation. Multiple principals can delegate a subset of their maximal permissions for the executable content. The mechanism uses policy for combining the delegated permissions into the content's runtime permissions.

Flexible and dynamic derivation of permissions

A cache system in accordance with the present invention consists of one or more cache components and a set of one or more consistency-replacement functions. A cache component caches one or more items in its one or more cache entries. Items that hit in the cache can result in corresponding cache entries being read or written. Any valid entry in a cache component includes status information reflecting whether the entry has been accessed and whether it has been modified, and is linked to a consistency-action matrix that, in correspondence with the entry's status information and access type (i.e. read or write), determines what consistency action has to be executed in conjunction with the current entry access. consistency actions and the consistency-action matrix are the inventive mechanisms for implementing cache-coherency and cache-replacement policies. Any valid entry in a cache is linked to a consistency-replacement function that implements one or more consistency and/or replacement policies. Consistency-replacement functions are application-specific and are implemented by means of the consistency-action matrix.

A mechanism for creating links and services on the Internet to reduce the bottlenecks at service providers by associating code with links to make them intelligent and a special protocol between the links and the back end servers to maintain scalableness and performance. Scalableness is supported by moving much of the functionality of searching onto the client side.

Growing community of inventors

Thornwood, NY, United States of America

Nayeem Islam